officedex
OfficeDex is the first Al-Native VibeOfficing platform for documents, slides, and spreadsheets
HYSEN LABS DIRECTORY
Curated AI & Machine Learning repositories with precise tags and practical analysis.
OfficeDex is the first Al-Native VibeOfficing platform for documents, slides, and spreadsheets
A comprehensive guide to adversarial testing and security evaluation of AI systems, helping organizations identify vulnerabilities before attackers exploit them.
An LLM-first SEO analysis skill for Antigravity, Codex, Claude with 16 specialized sub-skills, 10 specialist agents, and 88 optional utility scripts used as evidence collectors.
Editor Code Assistant (ECA) - AI pair programming capabilities agnostic of editor
33 battle-tested marketing skills for OpenClaw agents — Powered by MyClaw.ai
A Python-first runtime layer for multi-agent systems, with persistent run state, streaming execution events, and a pluggable orchestration interface.
Agents-flex is A lightweight Java AI agent development framework (positioned as a counterpart to Spring AI). It supports features such as RAG, MCP, Skills, Text2SQL , LLM Wiki, Sub-agents, Web Search, TTS (synchronous and streaming), and STT.
Data quality assessment and metadata reporting for data frames and database tables
🔥 On-Policy Self-Distillation in Diffusion Models
A version of verl to support diverse tool use [TMLR 2026]
Best-Effort Extent-Same, a btrfs dedupe agent
A pytorch quantization backend for optimum
Matkap - hunt down malicious Telegram bots
Open-source orchestrator and ADE for running Claude Code, Codex, OpenCode, Pi and other AI coding agents in parallel — locally or 24/7 on your own server.
a desktop app for getting work done with any model
Plan, build and launch products with AI: guided planning prompts, an AI App Starter for Next.js, Supabase and Vercel, and agent configurations.
Self-hosted AI gateway for coding CLIs — one OpenAI/Claude/Gemini/Codex-compatible endpoint, with a multi-tenant web console, request logs, and spend quotas.
A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
The Hitchhiker's Guide to Data Science for Social Good